Frequently asked questions
Is this an official Google service?
No. VoxCove is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, Google, or any other brand. Our infrastructure is built specifically for advertising agencies producing radio spots, offering predictable pricing and transparent delivery without relying on external brand ecosystems.
How many characters can I send per request?
You can send up to 4096 characters per request. For longer texts, split the input into parts of this limit and join the resulting audio files. This ensures consistent processing and allows you to manage character counts precisely against your billing balance.
Does the API support SSML?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control pacing and tone by adjusting the speed parameter between 0.25 and 4.0. For specific delivery nuances, select from the eight available voice presets that match your creative needs.
Can I clone a specific voice?
No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech.
What is the maximum speed setting?
The maximum speed setting is 4.0. You can adjust the speed parameter anywhere from 0.25 to 4.0. This allows you to control the delivery pace of the generated audio.
Are failed requests charged?
No. If synthesis fails, the charge is returned in full. You only pay for successful generations. Failed requests do not deduct from your balance, ensuring you are billed strictly for delivered audio files produced by the API.
How long is the free trial valid?
The free trial is valid for 7 days. It provides $0.50 of credit, allowing approximately 50,000 characters. This trial is available when you sign in with Google. Accounts created with email and password start without this trial credit.
Can I use the API for commercial radio ads?
Yes. The API is built for advertising agencies producing radio spots and voiceovers. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. You can generate audio files directly for commercial use without additional licensing hurdles.
Do I need a minimum spend?
No. There are no monthly plans, no seats, and no minimum spend. You top up with USDT on the TRON network, with a minimum of $5. Balance does not expire, and you only pay for the characters you actually use.
Is there a WordPress plugin?
No. We do not offer a WordPress plugin, browser extension, or official SDK. You can use the OpenAI SDKs by changing the base_url to our API endpoint, or use plain HTTP requests. Our documentation provides ready curl examples for immediate integration.
Does the API support streaming audio?
No. The API does not support streaming, WebSocket connections, or real-time partial audio. You send text and receive a complete audio file. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins.
What happens if I exceed the rate limit?
You are limited to 60 requests per minute per key (10 per minute before the first top-up). Requests are processed one after another. Requests are processed one after another, so under load a request may wait in a queue.
Are the voices licensed for commercial use?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and from LibriVox public-domain audiobook readings. This infrastructure handles high-volume character processing, making it suitable for commercial advertising agencies producing radio spots and voiceovers at scale.
How do I pay for the API?
Pay with USDT on the TRON network (TRC-20) only. There are no cards, PayPal, subscriptions, or invoices with VAT. Top-ups are credited automatically within minutes. The price is $10 per 1 million characters, with failed requests free.
First request
curl
curl https://api.3phase.info/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why agencies switch to our TTS API
Agencies generate voiceovers at scale, making per-character billing more predictable than per-minute models. You pay $0.01 per 1,000 characters, with failed requests free. This eliminates waste on long, unused radio spots.
Unlike monthly plans, there are no minimum spend requirements or recurring fees. You only pay for what you synthesize, keeping overhead low for variable campaign volumes.
Predictable per-character billing
Costs correlate directly with text length, not audio duration. A 4,096-character request generates roughly 30 seconds of audio, costing $0.04. This allows precise budgeting for high-volume spot production without surprise charges.
- Flat rate: $0.01 per 1,000 characters
- Failed requests incur zero cost
- Spaces and punctuation count as characters
No minimum spend or monthly fees
There are no monthly subscriptions or seat limits. Start with the free trial credit or top up with USDT (TRC-20). Balance never expires, allowing you to pause campaigns without losing unused funds.
- No monthly plans
- No minimum spend
- No per-seat licensing
OpenAI SDK compatible integration
Use the official OpenAI SDKs by pointing the base URL to https://api.3phase.info/v1. The request shape matches the standard speech endpoint, enabling rapid integration into existing agency workflows with minimal code changes.
- Same JSON structure as OpenAI
- Works with official OpenAI SDKs
- Simple base URL configuration
Audio quality for radio spots
We synthesize radio spots with natural intonation and pacing, ensuring the delivery matches professional voiceover standards. Our engine handles text up to 4,096 characters, allowing for complex scripts without awkward cuts. The generation time is roughly real-time, enabling efficient batch processing for campaign assets.
Natural intonation and pacing
Text is processed to maintain conversational flow, avoiding the monotony typical of basic TTS. Speed can be adjusted between 0.25x and 4.0x to fit specific timing constraints for 30 or 60-second spots. Requests are processed sequentially, so under load, a queue may form, but the output remains consistent.
Consistent voice profiles
We offer 8 distinct voice presets, including female options like Aria and Nova, and male options like Felix and Milo. Each voice maintains its specific tonal character across all generated files, ensuring brand consistency across multiple ads. Voices are based on licensed recordings from LibriTTS-R and LibriVox.
- Aria: Warm, clear narrator
- Felix: Energetic, promo style
- Atlas: Neutral, news style
No robotic artifacts
Audio files are generated with clear, broadcast-ready tones suitable for radio and digital playback. Every file carries an inaudible watermark to mark it as synthetic speech. We do not promise SLA-backed uptime or real-time streaming, but our infrastructure is built for reliable, high-volume character processing.
Technical integration
We provide a standard JSON API compatible with OpenAI SDKs. Send a POST request to https://api.3phase.info/v1/audio/speech with your model, input text, voice preset, and desired response format. Authentication requires a Bearer token issued via your account dashboard.
Simple JSON API endpoint
The endpoint accepts standard JSON bodies with fields like model, input, voice, response_format, speed, and optional language. Use the official OpenAI Python or Node SDKs by pointing base_url to https://api.3phase.info/v1 and supplying your API key. This eliminates custom client code for basic integration.
- POST to /v1/audio/speech
- Standard JSON request body
- Bearer token authentication
Support for MP3, WAV, OPUS, FLAC, and PCM
Select your preferred audio format directly in the request. We support MP3, WAV, OPUS, FLAC, and PCM output. This flexibility allows agencies to choose lossy formats for web delivery or lossless WAV/FLAC for high-quality radio broadcast masters without post-processing conversion.
Fast generation times
Generation typically matches real-time speed, processing approximately 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so high-volume bursts may enter a queue. Use the /v1/voices endpoint to verify available formats and speeds before implementation.
Voice catalog for advertising
Our infrastructure delivers eight distinct voice presets engineered for advertising clarity. Each voice is synthesized from licensed LibriTTS-R recordings, ensuring consistent audio profiles across high-volume radio spot production.
8 distinct voice presets
We provide eight specific voice models: Aria, Nova, Luna, and Sage for female tones; Felix, Milo, Atlas, and Orion for male tones. These presets cover a spectrum from warm narration to energetic promo styles, allowing agencies to match tone to brand identity without custom design.
Male and female options
The catalog includes four female and four male voices, each with distinct characteristics. Aria offers a clear narrator style, while Felix provides an energetic promo sound. Milo delivers a friendly conversational tone, and Atlas ensures neutral news delivery. This variety supports diverse casting needs within a single API integration.
Clear, broadcast-ready tones
Voices are derived from public-domain audiobook readings, optimized for clarity and natural intonation. Each generated file includes an inaudible watermark marking it as synthetic speech. The output is clean, free of robotic artifacts, and ready for direct insertion into broadcast workflows.
Language support
Our API supports 23 languages, enabling agencies to produce localized radio spots without managing multiple voice providers. Each voice preset delivers consistent, broadcast-ready quality across all supported regions, ensuring tonal coherence in multi-market campaigns.
23 languages available
Supported languages include Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, allowing flexible casting for diverse target audiences.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic language detection
If the language field is omitted, the system guesses the language from the script. Latin script text defaults to English, reducing configuration overhead for English-dominant spots.
Manual language override
For non-English Latin-script text, set the language parameter explicitly to ensure correct pronunciation. This prevents misinterpretation of accents or proper nouns in international campaigns.

Pricing model
VoxCove charges $0.01 per 1,000 characters, including spaces and punctuation. This linear scaling eliminates monthly commitments or minimum spend requirements, allowing agencies to pay strictly for what they consume. A free trial of $0.50 (approx. 50,000 characters) is available for 7 days upon Google sign-in.
$0.01 per 1,000 characters
Billing is calculated based on character count, not request volume. With a 4,096-character limit per request, long scripts are split and processed sequentially. The cost remains predictable regardless of audio format or speed settings.
Failed requests are free
If synthesis fails, the charge is returned in full. You only pay for successfully generated audio files, ensuring that infrastructure hiccups do not impact your production budget.
No hidden fees
There are no subscriptions, seats, or VAT invoices. Top-ups are processed via USDT (TRC-20) with a $5 minimum, credited automatically within minutes. Balance never expires.
Usage limits
Our infrastructure enforces a rate limit of 60 requests per minute per API key. This ensures consistent performance during high-volume campaigns, preventing sudden spikes from degrading audio quality for your entire agency. For new accounts before the first top-up, this limit is temporarily reduced to 10 requests per minute.
Each request supports a maximum of 4,096 characters. For longer scripts, split the text into chunks, synthesize each part, and join the resulting audio files. This approach maintains headroom for future API updates and ensures reliable delivery for full-length radio spots or voiceovers.
60 requests per minute
The standard rate limit is 60 requests per minute per active key. This allows agencies to process requests up to the limit, though they are processed sequentially. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed.
- Limit applies per API key
- Standard limit: 60 requests/minute
- New account limit: 10 requests/minute
4096 character limit per request
Each API call accepts up to 4,096 characters, including spaces and punctuation. For longer scripts, split the text into parts, generate audio for each, and concatenate the results. This method ensures predictable processing times and avoids hitting character caps mid-sentence.
Longer texts are processed at roughly real-time speed (25 characters per second). Short phrases may take a few seconds to generate. The 4,096-character limit helps manage these processing windows efficiently.
Queue processing under load
Requests are processed sequentially within the rate limit window. During high demand, your request may wait in a queue before synthesis begins. This ensures fair resource distribution and consistent audio quality, though it may introduce slight delays during peak usage periods.
Data and privacy
Our system uses input text solely to generate the audio file. The raw text is not ingested into training datasets or used to improve the underlying model, ensuring your copy remains proprietary.
Text not used for training
Unlike many consumer-grade services, your script data is treated as a transient input. It is processed to synthesize the audio and is not retained for machine learning purposes, keeping your creative assets distinct from our model improvements.
Audio not stored
Generated audio files are returned directly in the API response and are not persisted on our servers after delivery. This minimizes storage overhead and ensures that your final radio spot files remain under your control, reducing long-term data liability.
Metadata kept for billing
We retain request metadata—specifically timestamp, character count, and status—to accurately calculate charges and verify usage. This data is used exclusively for billing transparency and does not contain the content of your scripts or the resulting audio.
Comparison with Google TTS
Agencies scaling production often find traditional providers impose volume tiers or minimum commitments. Our model charges strictly per character, removing the friction of overage fees or unused credits. This structure ensures that high-volume radio spot generation remains predictable without monthly overhead.
The API mirrors the OpenAI request shape, allowing agencies to swap in the endpoint by changing the base URL. This compatibility lets teams reuse existing OpenAI SDK integrations without rewriting their pipeline logic, reducing integration time and technical debt.
Lower cost at scale
At $0.01 per 1,000 characters, costs remain linear regardless of volume. Unlike tiered plans that complicate budgeting, you only pay for what you generate. Failed requests are free, ensuring you do not pay for wasted compute.
This pricing model suits agencies producing dozens of radio spots daily. You avoid the minimum spend requirements common in enterprise voice contracts, keeping cash flow flexible for campaign fluctuations.
- Linear pricing: $0.01 per 1,000 characters.
- No minimum spend or monthly fees.
- Failed requests are free.
Simpler API structure
The endpoint accepts standard JSON bodies with model, input, and voice fields. Agencies can integrate using the official OpenAI SDK by changing the base_url to https://api.3phase.info/v1. This reduces boilerplate code and leverages existing client libraries.
You do not need to learn a proprietary protocol or handle complex authentication flows beyond a standard Bearer token. The request shape matches industry standards, making onboarding new developers straightforward.
- OpenAI SDK compatible.
- Standard JSON request body.
- Simple Bearer token authentication.
Transparent usage metrics
Every request returns clear metadata on character count and status. You can track exactly how many characters were processed per spot, enabling precise cost forecasting for each campaign asset.
The /v1/voices and /v1/models endpoints provide immediate access to available options and formats. There are no hidden fees for format conversions or speed adjustments within the supported range.
- Clear character count per request.
- No hidden format fees.
- Real-time status codes.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice is derived from licensed recordings, providing a consistent baseline for quality.
23 languages
Any voice speaks any of these languages.
